INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

áº¥p

-0.15

ihar

-0.14

Ã¥

-0.14

Sly

-0.14

rar

-0.14

chal

-0.14

ousy

-0.13

 ç¼

-0.13

aney

-0.13

arent

-0.13

POSITIVE LOGITS

olini

0.17

 Bylo

0.16

achs

0.15

stoi

0.15

ioni

0.14

ellas

0.14

ordo

0.14

 incoming

0.14

ohen

0.14

dee

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.